Scribd Logo
Upload

Welcome to Scribd!

  • 333 views

    Hypothesis Testing Examples

    Uploaded by

    Senthil
    The document contains four statistical tests: 1. A one-sample t-test to test if the average age of an insurance agent's policyholders is less than 30.5 years. The null hypothesis is rejected, supporting the agent's claim. 2. A two-sample t-test to test for differences in waiting times between two bank branches. The null hypothesis of no difference is rejected. 3. A chi-square test of independence to test if gender and education level are related. The null hypothesis of independence is rejected. 4. A one-way ANOVA to test for differences in waiting times across three bank branches. The null hypothesis of no differences is rejected.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Hypothesis Testing Examples

    Uploaded by

    Senthil
    333 views5 pages
    The document contains four statistical tests: 1. A one-sample t-test to test if the average age of an insurance agent's policyholders is less than 30.5 years. The null hypothesis is rejected, supporting the agent's claim. 2. A two-sample t-test to test for differences in waiting times between two bank branches. The null hypothesis of no difference is rejected. 3. A chi-square test of independence to test if gender and education level are related. The null hypothesis of independence is rejected. 4. A one-way ANOVA to test for differences in waiting times across three bank branches. The null hypothesis of no differences is rejected.

    Original Description:

    na

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    The document contains four statistical tests: 1. A one-sample t-test to test if the average age of an insurance agent's policyholders is less than 30.5 years. The null hypothesis is rejected, supporting the agent's claim. 2. A two-sample t-test to test for differences in waiting times between two bank branches. The null hypothesis of no difference is rejected. 3. A chi-square test of independence to test if gender and education level are related. The null hypothesis of independence is rejected. 4. A one-way ANOVA to test for differences in waiting times across three bank branches. The null hypothesis of no differences is rejected.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    333 views5 pages

    Hypothesis Testing Examples

    Uploaded by

    Senthil
    The document contains four statistical tests: 1. A one-sample t-test to test if the average age of an insurance agent's policyholders is less than 30.5 years. The null hypothesis is rejected, supporting the agent's claim. 2. A two-sample t-test to test for differences in waiting times between two bank branches. The null hypothesis of no difference is rejected. 3. A chi-square test of independence to test if gender and education level are related. The null hypothesis of independence is rejected. 4. A one-way ANOVA to test for differences in waiting times across three bank branches. The null hypothesis of no differences is rejected.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 5

    1.

    Test for a single mean (Large sample)

    Ref: Statistics for Managers, 8th Ed., Levine et.al

    An insurance agent has claimed that the average age of policyholders who insure through him is less
    than the average for all agents, which is 30.5 years. A random sample of 100 policyholders who had
    insured through him gave the following age distribution.

    Age No. of persons


    15.5 – 20.5 12
    20.5 – 25.5 22
    25.5 – 30.5 20
    30.5 – 35.5 30
    35.5 – 40.5 16
    Total 100

    Test the agent’s claim at 5% level of significance.

    Solution

    Mid point
    Lower Upper (x) freq(f) x.f x^2 f
    15.5 20.5 18 12 216 3888
    20.5 25.5 23 22 506 11638
    25.5 30.5 28 20 560 15680
    30.5 35.5 33 30 990 32670
    35.5 40.5 38 16 608 23104
    Total 100 2880 86980
    Mean 28.8
    Variance 40.76767677
    SD 6.384957069
    SE 0.638495707
    Z -2.66250811
    Ho rejected

    Sample size = n = 100; Sample Mean = 𝑥̅ = 28.8 years; Sample SD = s = 6.45 years

    Null Hypothesis: Ho: μ = 30.5 against the alternative hypothesis H1: μ < 30.5

    𝑥̅ −𝜇 𝑠
    Test Statistic: Z = , where SE(𝑥̅ )= ; Reject Ho at 5% level if (and only if) Z < -1.645
    𝑆𝐸(𝑥̅ ) √𝑛

    Here SE(𝑥̅ ) = 6.45/√100 = 0.645; Z = (28.8 – 30.5)/0.645 = - 2.636

    Since Z is less than -1.645, we reject Ho at 5% level; and conclude that the insurance agent’s
    claim is valid.
    2. Test for difference of two means

    One measure of the performance of bank branches is the waiting time for the arriving customers. In
    a study of waiting time for serving customers in two branches of a bank, 15 customers from each
    branch have been randomly selected, and waiting times are recorded as follows:

    Branch 1: 4.21 5.55 3.02 5.13 4.77 2.34 3.54 3.20 4.50 6.10

    0.38 5.12 6.46 6.19 3.79

    Branch 2: 9.66 5.90 8.02 5.79 8.73 3.82 8.01 8.35 10.49 6.68

    5.64 4.08 6.17 9.91 5.47

    Assuming that the population variances from both branches are equal, is there evidence of a
    difference in the mean waiting time between the two branches? Use 5% level of significance.

    Solution

    Branch 1 Branch 2

    Mean 4.286667 Mean 7.114667


    Standard Deviation 1.637985 Standard Deviation 2.082189
    Sample Variance 2.682995 Sample Variance 4.335512
    Count 15 Count 15

    Assuming a common unknown population variance, the pooled estimate of the common variance

    (𝑛1−1) 𝑠12 +(𝑛2−1)𝑠22 1 1


    𝑠= √ = 1.873366; SE(Mean difference) = s√ +
    𝑛1+𝑛2−2 𝑛1 𝑛2

    Null Hyp: Ho: µ1=µ2; Alternative Hyp H1: µ1≠µ2

    ̅̅̅̅
    ̅̅̅̅−𝑥2
    𝑥1
    Test Statistics: t = = -4.13416; Degrees of Freedom = n1+n2-2 = 28
    𝑆𝐸

    5% Tabled value of t with 28 DF (two-tailed) = 2.048

    We shall reject Ho if (and only if) observed absolute t > tabled t

    Here Absolute t = 4.13416 > 2.048, so we reject Ho

    Difference in the mean waiting time between the two branches is significantly different at 5% level
    of significance
    3. Test for Goodness of Fit

    Is gender independent of education level? A random sample of 395 people


    were surveyed and each person was asked to report the highest education
    level they obtained. The data that resulted from the survey is summarized
    in the following table:

    High School Bachelors Masters Ph.d. Total


    Female 60 54 46 41 201
    Male 40 44 53 57 194
    Total 100 98 99 98 395
    Question: Are gender and education level dependent at 5% level of
    significance? In other words, given the data collected above, is there a
    relationship between the gender of an individual and the level of education
    that they have obtained?

    Here's the table of expected counts:

    High School Bachelors Masters Ph.D. Total


    Female 50.886 49.868 50.377 49.868 201
    Male 49.114 48.132 48.623 48.132 194
    Total 100 98 99 98 395

    So, working this out, χ2=(60−50.886)2/50.886+⋯+(57−48.132)2/48.132=8.006

    The critical value of χ2 with 3 degree of freedom is 7.815. Since 8.006 >
    7.815, therefore we reject the null hypothesis and conclude that the
    education level depends on gender at a 5% level of significance.
    4. Test for equality of more than two means (One way ANOVA)

    In Problem 2, we have seen how we compare whether the means of two populations are
    equal or not. A natural question that arises is: what we do if we need to compare the means
    of more than two populations.
    Continuing from Problem 2, suppose data on waiting time of 12 customers for one more
    branch, say Branch 3, is available.

    Branch 1: 4.21 5.55 3.02 5.13 4.77 2.34 3.54 3.20 4.50 6.10

    0.38 5.12 6.46 6.19 3.79

    Branch 2: 9.66 5.90 8.02 5.79 8.73 3.82 8.01 8.35 10.49 6.68

    5.64 4.08 6.17 9.91 5.47

    Branch 3: 7.25 6.92 6.16 8.25 5.59 9.93 11.21 10.29 11.68 9.95

    8.88 7.97

    Assuming that the population variances from all branches are equal, is there evidence of a
    difference in the mean waiting time among the three branches? Use 5% level of significance.

    Supposing the means are µ1, µ2, and µ3. We may be interested to test the null hypothesis

    Ho: µ1= µ2= µ3 against the alternative Ha: they are unequal.

    The technique by which this can be carried out is called Analysis of Variance (ANOVA). We
    assume that the underlying population variances are all equal, but unknown.

    Anova: Single Factor

    SUMMARY
    Groups Count Sum Average Variance
    Branch 1 15 64.3 4.286667 2.682995238
    Branch 2 15 106.72 7.114667 4.335512381
    Branch 3 12 104.08 8.673333 3.903442424

    ANOVA
    Source of Variation SS df MS F P-value F crit
    Between Groups 135.7254 2 67.86271 18.74435236 1.97521E-06 3.238096135
    Within Groups 141.197 39 3.620435

    Total 276.9224 41

    You might also like